Natural language processing based on textual polarity

Abstract

Natural language processing (NLP) with awareness of textual polarity. An NLP system, such as a search engine or a Question-Answering (QA) system receives input text for processing. The input text may be a text fragment, a search phrase, a question having a general type, or a polar question having a yes or no answer. The NLP system identifies textual polarity and provides responses to the input text (for example, in answer form) based on identifying evidence whose selection, scoring, and processing, is informed by the textual polarity of the input text, and the textual polarity of candidate evidence passages.

What is claimed is: 
     
       1. A method for performing a textual query by a search engine, comprising:
 receiving an electronic input text having a polarity value; 
 identifying the polarity value of the electronic input text based on a polarity of a textual element of the electronic input text, wherein the identifying is based on determining that a change in the polarity of the textual element changes the polarity of the electronic input text and wherein the polarity of the textual element gives a meaning to the electronic input text; 
 generating a modified electronic input text by replacing the textual element of the electronic input text with a lexical substitute; wherein a polarity value of the modified electronic input text is different from the polarity value of the electronic input text, and wherein a meaning of the modified electronic input text is different from the meaning of the electronic input text; 
 searching a database using at least a portion of the modified electronic input text as a query; and 
 receiving search results based on the searching. 
 
     
     
       2. The method of  claim 1 , further comprising:
 ranking the received search results relative to one another. 
 
     
     
       3. The method of  claim 2 , wherein the ranking is based on the polarity value of the electronic input text relative to polarity values of the received search results. 
     
     
       4. The method of  claim 2 , further comprising:
 excluding from search results at least one search result having a polarity value that is opposite to the polarity value of the electronic input text. 
 
     
     
       5. The method of  claim 2 , wherein identifying the polarity value of the electronic input text comprises:
 detecting a polar word in the electronic input text based on the polar word matching at least one criterion for a polar term; and 
 identifying the polarity value of the electronic input text based on the detecting. 
 
     
     
       6. The method of  claim 2 , wherein identifying the polarity value of the electronic input text is based on:
 generating a predicate-argument structure (PAS) for the electronic input text; 
 comparing a pattern in the PAS to one or more patterns in a set of pattern matching rules, the set of pattern matching rules comprising predetermined PAS patterns; and 
 identifying at least one polar word based on the comparing resulting in a match between the pattern in the PAS to at least one of the one or more patterns in the set of pattern matching rules. 
 
     
     
       7. The method of  claim 1 , further comprising:
 querying a database using one or more words in the electronic input text; 
 receiving one or more candidate passages in response to the query; and 
 scoring the one or more candidate passages.